Senior AI Engineer

CommodityAI•San Francisco, CA
•$200,000 - $250,000•Hybrid

About The Position

CommodityAI is looking for a senior engineer to build agents that use modern models to carry out useful work with increasing autonomy. The role focuses on building the harnesses around models—including tools, context, execution loops, state and feedback—that help agents complete tasks across CommodityAI’s product and connected systems. You will prototype capabilities, test them against customer problems, and use evaluations and production traces to decide what is ready to run autonomously and what needs further development. This is a hands-on engineering role with ownership from early experiments through reliable production behavior. You will work closely with the founders and customers, own meaningful parts of the product, and help scale the work the product and team can accomplish.

Requirements

  • Strong software engineering skills and experience building working agent systems that take actions and complete tasks.
  • Practical understanding of how harness design, context management and tool interfaces affect model performance.
  • Experience creating evaluations, reading execution traces and systematically improving unreliable behavior.
  • Ability to move quickly from an idea to a working feature and make deliberate decisions about what to harden for production.
  • Good judgment about agent autonomy, including how to bound actions and when to involve a person.
  • Product curiosity and ownership, with willingness to stay responsible for a system after launch.

Nice To Haves

  • Experience with long-running agents, durable execution, state management, retries and recovery.
  • Experience with coding agents, browser or computer-use agents, or agents that work across multiple tools and APIs.
  • Experience building evaluation harnesses, task environments or tools for inspecting and replaying agent runs.
  • Experience shipping model-powered features on a small team and keeping pace with changes in model capabilities.

Responsibilities

  • Build agent harnesses that provide models with the tools, context and execution environment to complete tasks across the product and connected systems.
  • Design how agents plan, act, maintain state, recover from failures and hand work back to a person when needed.
  • Prototype model- and agent-based features, test them against customer problems, and turn promising experiments into shipped capabilities.
  • Build evaluations for task completion and decision and action quality; convert production failures into reproducible cases to improve future iterations.
  • Inspect execution traces and debug prompts, context, tool interfaces, orchestration and model behavior.
  • Increase useful autonomy over time using clear permissions, checkpoints and human intervention where required.
  • Experiment with models and approaches, measuring their capability, reliability, latency and cost in actual workflows.
  • Create reusable tools and harness components so features are easier to build and operate and the team can support more customers without repeating manual work.

Benefits

  • 0.25%–0.5% equity
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service